IE 4362 JMP2_F23(1)

docx

School

Louisiana State University *

*We aren’t endorsed by this school

Course

4362

Subject

Industrial Engineering

Date

Dec 6, 2023

Type

docx

Pages

4

Uploaded by SuperHumanDiscoveryPigeon35

Report
IE 4362 JMP Assignment 2 Due Nov. 14, 2023 at 10:30am on Moodle Directions: Type your responses to each question in a Word document. All analysis should be completed using JMP. Type all answers and use JMP-generated tables and graphs in a single Word document. Show all steps and all work. You may assume an alpha level of 0.05 unless otherwise noted. To answer each question, copy the output from JMP, showing enough detail to understand the analysis setup and the critical output used to answer the question. Then, type your answer based on this output, even if it means repeating the same numbers shown in the JMP output. This is your formal answer, supported by analysis in JMP. There are 105 points total in this assignment. Points are broken down by problem. Exception: you do not need to write out equations and numbers for finding means and standard deviations. Submitting your assignment: Put your name in the upper left corner of the first page. Upload one pdf document to Gradescope using the link in Moodle by 10:30am on Nov. 14, 2023. The file name must be in the following format: LastNameFirstInitial_JMP1.docx or .pdf (10% penalty otherwise). Module 3 Problem 1 (47 points): The data from a patient satisfaction survey from one hospital are shown in the table below. The hospital management wants to determine predictors of satisfaction and has asked you to investigate. You will develop a multiple linear regression with satisfaction as the output and the remaining variables (age, severity, surg-med, and anxiety) as potential variables (inputs). Surg-Med indicates whether a patient was there as a surgical patient (1) or a medical patient (0). Higher numbers indicate higher severity, higher anxiety, and higher satisfaction. Observatio n Ag e Severit y Surg- Med Anxiet y Satisfaction 1 55 50 0 2.1 68 2 46 24 1 2.8 77 3 30 46 1 3.3 96 4 35 48 1 4.5 80 5 59 58 0 2 43 6 61 60 0 5.1 44 7 74 65 1 5.5 26 8 38 42 1 3.2 88 9 27 42 0 3.1 75 10 51 50 1 2.4 57 11 53 38 1 2.2 56 12 41 30 0 2.1 88 13 37 31 0 1.9 88 14 24 34 0 3.1 102 15 42 30 0 3.1 88 16 50 48 1 4.2 70
17 58 61 1 4.6 52 18 60 71 1 5.3 43 19 62 62 0 7.2 46 20 68 38 0 7.8 56 21 70 41 1 7 59 22 79 66 1 6.2 26 23 63 31 1 4.1 52 24 39 42 0 3.5 83 25 49 40 1 2.1 75 1. First examine the dataset to determine which variables are meaningful and which might be correlated (and therefore unnecessary). Do this through 2 steps. You do not need to include the Surg-Med variable in these steps. a. (8) Examine the correlations between the input variables. Show the correlations table and discuss the relationship between each pair in terms of direction and strength. b. (12) Develop a scatterplot and simple linear regression model between satisfaction and each input variable. Discuss which variables appear to have a meaningful impact on satisfaction, and how you came to that conclusion. 2. Conduct a forward stepwise regression to find the best model of satisfaction from the 4 input variables provided. Include the Surg-Med variable as a categorical variable. a. (2) Based on the scatterplots and simple linear regressions developed in 1.b., which variable should be entered first? (Ignore the Surg-Med variable for this question.) b. (5) Show the JMP output for the final model. c. (5) Discuss the fit of the overall model using at least two analyses from the output. In particular, how much variance in the data is explained by this model? d. (3) How much variance is NOT explained by the model? Provide a number, and list a few potential causes for the unexplained variance. 3. (6) Write the final model equation and specify the ranges of each variable for which the model is valid. 4. Evaluate the final model: a. (3) Would you recommend that management use this model to predict satisfaction? Give a yes/no answer and reasoning. b. (3) If you wanted to improve satisfaction, how could you use this model? What programs or initiatives might be helpful?
Module 4 Problem 2 (33 points total): You are studying the outcomes of various styles of training programs for technicians. Twenty-three technicians were randomly assigned to one of five training types. Scores on the quality of their next job after training were recorded below, with higher scores meaning a higher quality outcome. Training Type Score 1 8 1 7 1 5 1 5 2 10 2 10 2 8 2 9 2 10 2 7 3 10 3 9 3 10 3 8 3 10 4 6 4 8 4 7 4 5 4 6 5 10 5 9 5 5 1. (5) Describe the data by creating a bar graph using JMP to display the means and standard errors of scores for each training type. 2. (1) What is the dependent variable (outcome) in this experiment? 3. (2) What is the independent factor, and how many levels are there? 4. (13) Determine if the dataset meets the three ANOVA assumptions. Show all JMP output and provide a conclusion for each assumption. Provide an overall conclusion to answer whether we can use ANOVA on this dataset.
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
5. (5) Assuming part 4 is satisfactory, run an ANOVA to see if there is a difference in scores. Show the JMP output. State which numbers are useful in concluding, and state your conclusion in practical language. 6. (4) Run a Tukey HSD test to determine if specific training types differ in scores. Show the JMP output and discuss which pairs are significantly different. 7. (3 points) Overall conclusion: Is there a difference between the training types on technician product quality? Provide discussion on which types are better or worse in terms of outcomes. Support your answer with both statistical (numerical) evidence and practical interpretation. Be concise: answer the questions directly. You do not need any formal hypothesis testing. Module 5, through 2c Problem 3 (25 points): A manufacturing engineer uses four different raw materials (1, 2, 3, and 4) and three different temperatures (1, 2, and 3) to produce copper wires, used in electric cables. The engineer wishes to study the effect of material and temperature on tensile strength of the wire. She replicates the experiment twice. You may assume that the model meets all assumptions necessary to perform ANOVA. The data is provided in the Moodle assignment (IE4362_JMP2_P3_ANOVA.jmp) Use an alpha level of 0.10 for this problem. 1. (5) Use JMP to graph the means with a standard error bar for the combinations of material and temperature. 2. (4) List the following variables for this experiment: a. Dependent factor(s): b. Main effect(s): c. Interaction effect(s): 3. Using ANOVA, determine which main and interaction effects affect tensile strength. a. (4) Show the JMP output for the ANOVA table and effects test table. b. (9) Discuss each effect you listed in part 2 by stating whether or not it is significant, a statistic that supports your conclusion, and an explanation of what that effect means for tensile strength. 4. (3) From a statistical perspective, which material-temperature combination would you recommend, if any, to produce the highest tensile strength? (Note there could be more than one combination that produces statistically equivalent strengths.) Provide reasoning for your answer.